Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    titles or headings referring to upcoming or related content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Next."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.66
    arist
    -0.62
     sided
    -0.61
    CVE
    -0.60
    arine
    -0.60
    wart
    -0.59
    inous
    -0.59
     jar
    -0.56
    warts
    -0.56
    oine
    -0.55
    POSITIVE LOGITS
     Next
    3.74
    Next
    2.81
     NEXT
    2.35
    next
    2.12
     next
    1.70
     Tomorrow
    1.54
     Then
    1.26
     Previous
    1.23
     Future
    1.21
     Later
    1.18
    Act Density 0.012%

    No Known Activations